English
Related papers

Related papers: Sparse Autoencoders enable Robust and Interpretabl…

200 papers

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Clément Cornet , Romaric Besançon , Hervé Le Borgne

In this paper, we propose a new method to enhance compositional understanding in pre-trained vision and language models (VLMs) without sacrificing performance in zero-shot multi-modal tasks. Traditional fine-tuning approaches often improve…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Youngtaek Oh , Jae Won Cho , Dong-Jin Kim , In So Kweon , Junmo Kim

Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive most fine-grained latent features for safety, a low-frequency…

Machine Learning · Computer Science 2026-04-15 Jiaqi Weng , Han Zheng , Hanyu Zhang , Ej Zhou , Qinqin He , Jialing Tao , Hui Xue , Zhixuan Chu , Xiting Wang

The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Ke Jin , Wankou Yang

Although massive pre-trained vision-language models like CLIP show impressive generalization capabilities for many tasks, still it often remains necessary to fine-tune them for improved performance on specific datasets. When doing so, it is…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Moritz Ibing , Isaak Lim , Leif Kobbelt

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and…

Computation and Language · Computer Science 2023-02-10 Alan Ansell , Edoardo Maria Ponti , Anna Korhonen , Ivan Vulić

Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they rely on expanding the representation dimension, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Piotr Kubaty , Patryk Marszałek , Łukasz Struski , Adam Wróbel , Jacek Tabor , Marek Śmieja

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith

Supervised fine-tuning methods (SFT) perform great efficiency on artificial intelligence interpretation in SAR images, leveraging the powerful representation knowledge from pre-training models. Due to the lack of domain-specific pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Xinyang Pu , Feng Xu

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Weiheng Zhao , Zilong Huang , Jiashi Feng , Xinggang Wang

Transformer-based CLIP models are widely used for text-image probing and feature extraction, making it relevant to understand the internal mechanisms behind their predictions. While recent works show that Sparse Autoencoders (SAEs) yield…

Machine Learning · Computer Science 2025-05-27 Maximilian Dreyer , Lorenz Hufe , Jim Berend , Thomas Wiegand , Sebastian Lapuschkin , Wojciech Samek

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

Recent advancements in Contrastive Language-Image Pre-training (CLIP) have demonstrated notable success in self-supervised representation learning across various tasks. However, the existing CLIP-like approaches often demand extensive GPU…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Yuexi Du , Brian Chang , Nicha C. Dvornek

Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making…

Machine Learning · Computer Science 2025-05-23 Bartosz Cywiński , Kamil Deja

Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input…

Machine Learning · Computer Science 2025-11-19 Ashwin Saraswatula , David Klindt

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has emerged as the standard post-training paradigm for large language models (LLMs). However, the conventional SFT process, driven by Cross-Entropy (CE) loss, often…

Computation and Language · Computer Science 2026-02-10 Yijie Chen , Yijin Liu , Fandong Meng

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based…

Computation and Language · Computer Science 2025-03-05 Zhengxuan Wu , Aryaman Arora , Atticus Geiger , Zheng Wang , Jing Huang , Dan Jurafsky , Christopher D. Manning , Christopher Potts

Artificial intelligence in healthcare requires models that are accurate and interpretable. We advance mechanistic interpretability in medical vision by applying Medical Sparse Autoencoders (MedSAEs) to the latent space of MedCLIP, a…

Artificial Intelligence · Computer Science 2026-05-25 Riccardo Renzulli , Colas Lepoutre , Enrico Cassano , Marco Grangetto
‹ Prev 1 3 4 5 6 7 10 Next ›